| commit | 4d1b80e107da81510ec15e9ca72569fc6cbbac72 | [log] [tgz] |
|---|---|---|
| author | Julia Wang <juliaw@apache.org> | Wed Jul 26 19:04:17 2017 -0700 |
| committer | Sergiy Matusevych <motus@apache.org> | Wed Aug 30 15:49:51 2017 -0700 |
| tree | 6b0df03e04bb50d95932673faaf5db209591e511 | |
| parent | d609c002c38032f55c915c72434ae1443604461b [diff] |
[REEF-1842] Making IMRU task and input data association deterministic * Use partitionDescriptor id as part of the context id so that context id is associated with a fixed partitionDescriptor. Please notice that the partition descriptor id always follows the pattern like RandomInputPartition-x and is unique * Make contexts stored in a sorted collection to ensure tasks with associated context/partitionDescriptor are always add to group in the same sequence. JIRA: [REEF-1842](https://issues.apache.org/jira/browse/REEF-1842) This closes #1346
Apache REEF™ (Retainable Evaluator Execution Framework) is a library for developing portable applications for cluster resource managers such as Apache Hadoop YARN or Apache Mesos. For example, Microsoft Azure Stream Analytics is built on REEF and Hadoop.
Detailed information on REEF can be found in the following places:
The developer mailing list is the best way to reach REEF‘s developers when the above aren’t sufficient.
| Component | OS | Status |
|---|---|---|
| REEF Java | Ubuntu |  |
| REEF.NET | Windows |
| Java | .NET | |
|---|---|---|
| Build & run unit tests | java\BUILD.md | cs\BUILD.md |
